Lead Agentic AI Engineer - FDE (Forward Deploy Engineer)
A Lead Agentic AI Engineer working as a Forward Deployed Engineer, embedded directly with business stakeholders, product leads and operations teams to turn complex institutional workflows into enterprise-grade autonomous agent solutions across platforms such as KYC Intelligence, Funds Lifecycle, Document Processing and Regulatory Compliance. The role is listed as hybrid.
What you'll do
- Design, prototype, evaluate and deploy multi-agent architectures, agentic tool orchestration (e.g. MCP, tool-calling pipelines), dynamic RAG retrieval and human-in-the-loop decision workflows.
- Turn ambiguous business problems into production-ready proofs of concept in 2–4 week cycles, then harden them for enterprise deployment.
- Sit alongside business heads, compliance officers and operations leads to find automation bottlenecks and design tailored AI agent interventions.
- Integrate agent services with Java/Python backend, UI and DevOps engineers into core transactional systems, CLM platforms and CI/CD pipelines.
- Lead the technical defense and documentation of agentic workflows through Model Risk Management, Responsible AI and InfoSec approval gates, and relay field feedback to the AI product roadmap.
What you bring
- 7+ years of software engineering, including 3+ years in applied NLP, GenAI, LLM application development and agent orchestration.
- Advanced Python (FastAPI, Asyncio, Pydantic, LangChain/LangGraph) plus Java/Spring Boot or modern TypeScript/Node.
- Experience building multi-agent systems (ReAct, Plan-and-Solve, stateful workflows, memory management, structured output parsing).
- Vector and relational databases (pgvector, Qdrant, Milvus, Pinecone), LLM APIs and gateways (AWS Bedrock, Azure OpenAI), Docker/Kubernetes/OpenShift, CI/CD and AWS/GCP.
- Bonus: institutional banking, FinTech, KYC/AML or fund operations experience; MCP or enterprise tool-calling frameworks; model risk governance.